akadmin/openwakeword
1
0
Fork 0
mirror of https://github.com/dscripka/openWakeWord.git synced 2026-08-27 18:17:20 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixed path issue and updated readme [skip ci]

Browse source
This commit is contained in:
dscripka 2023-03-04 23:47:44 -05:00
parent 4eaebb16e1
commit 9f19d307d8
2 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/README.md
View file

@ -28,6 +28,9 @@ pip install PyAudioWPatch scipy
2) Run the script: `python capture_activations.py --threshold 0.5 --output_dir <my_dir> --model <my_model>`
Where `--output_dir` is the desired location to save the activation clips, and `--model` is the model name or full path of the model to use.
If `--model` is not provided, all of the default models will be loaded.
Note that if you have more than one microphone connected to your system, you may need to adjust the PyAudio configuration in the script to select the appropriate input device.
## Benchmark Efficiency

4
examples/capture_activations.py
View file

@ -145,10 +145,10 @@ if __name__ == "__main__":
print(f'Detected activation from \"{mdl}\" model at time {detect_time}!')
# Capture total of 5 seconds, with the mic_ associated with the
# Capture total of 5 seconds, with the microphone audio associated with the
# activation around the ~4 second point
audio_context = np.array(list(owwModel.preprocessor.raw_data_buffer)[-16000*5:]).astype(np.int16)
fname = detect_time + f"_{mdl}.wav"
scipy.io.wavfile.write(os.path.join(os.path.abspath(args.output_dir), fname), 16000, audio_context)
playBeep('audio/activation.wav', audio)
playBeep(os.path.join(os.path.dirname(__file__), 'audio', 'activation.wav'), audio)